Views
No views yet
ornith:35b teacher's self-scaffolds, so a small local model can produce the structured plans
that le-harnais's lh harness self-scaffold step executes and verifies.meta-llama/Llama-3.2-3B-Instruct — Built with Llama; Llama 3.2 Community License applies.heroornith:9b/ornith:35b family (MIT) — scaffolds generated by ornith:35b.(task → verify-tagged numbered plan) pairs from the teacher (38 held-out).--self-scaffold path (which on a weak policy halved
escalation in an A/B), with no RL and no remote model.1# 1. corpus from the teacher, 2. full-FT distill, 3. held-out bench
2python tools/gen_ornith_scaffold_corpus.py --n 160 --eval 40 --out datasets/ornith_scaffold
3BASE=meta-llama/Llama-3.2-3B-Instruct OUT=refs/llm-jepa/ft-ornith-scaffold-3b \
4 tools/distill_ornith_scaffold.sh
5python tools/bench_scaffold.py --student refs/llm-jepa/ft-ornith-scaffold-3b \
6 --base meta-llama/Llama-3.2-3B-Instruct --eval datasets/ornith_scaffold_eval.jsonldocs/ornith-self-improving.md (D1–D4) and docs/local-coding-agents-bench.md
in the [le-harnais] repo. Serve with transformers or le-harnais lh-serve/candle.Distilling a teacher's scaffolding skill into a small student: structure and plan quality transfer; this is behavior distillation, not the teacher's RL.